Using deep learning for ordinal classification of mobile marketing user conversion

In this paper, we explore Deep Multilayer Perceptrons (MLP) to perform an ordinal classification of mobile marketing conversion rate (CVR), allowing to measure the value of product sales when an user clicks an ad. As a case study, we consider big data provided by a global mobile marketing company. S...

ver descrição completa

Detalhes bibliográficos
Autor principal: Matos, Luís Miguel (author)
Outros Autores: Cortez, Paulo (author), Mendes, Rui (author), Moreau, Antoine (author)
Formato: conferencePaper
Idioma:eng
Publicado em: 2019
Assuntos:
Mobile Performance Marketing
Multilayer Perceptron
Ordinal Classification
Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
Science & Technology
Texto completo:http://hdl.handle.net/1822/62742
País:Portugal
Oai:oai:repositorium.sdum.uminho.pt:1822/62742
Descrição
Resumo:In this paper, we explore Deep Multilayer Perceptrons (MLP) to perform an ordinal classification of mobile marketing conversion rate (CVR), allowing to measure the value of product sales when an user clicks an ad. As a case study, we consider big data provided by a global mobile marketing company. Several experiments were held, considering a rolling window validation, different datasets, learning methods and performance measures. Overall, competitive results were achieved by an online deep learning model, which is capable of producing real-time predictions.

Registros relacionados